© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 80889
    Prev
    Next
    INDEX
    Explanations

    patterns or symbols resembling formatting elements and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ILT
    -0.08
     ↵↵
    -0.07
    eor
    -0.06
    .ly
    -0.06
    amt
    -0.06
    LY
    -0.06
    amos
    -0.06
    ÚĨÙĩ
    -0.06
    ↵↵
    -0.06
    ÑģÑı
    -0.06
    POSITIVE LOGITS
    zano
    0.07
    activex
    0.07
    ://
    0.07
     Latter
    0.06
     commerc
    0.06
    marca
    0.06
    ecast
    0.06
    ¢
    0.06
     Heller
    0.06
    aggio
    0.06
    Activations Density 0.000%

    No Known Activations